kallithea Changeset - e708b26819cd

Changeset - e708b26819cd

Parent rev.

Child rev.

[Not reviewed]

default

0 1 0

Mads Kiilerich - 8 years ago 2017-10-03 00:14:40
mads@kiilerich.com

diffs: move _escaper to a pure function

It used to count diff size - now it is a clean function.

1 file changed with 28 insertions and 25 deletions:

kallithea/lib/diffs.py

0 comments (0 inline, 0 general)

kallithea/lib/diffs.py

➞

Show inline comments

@@ @@ -296,91 +296,67 @@ class DiffProcessor(object): @@
            ^rename[ ]to[ ](?P<rename_to>.+)(?:\n|$))?
         (?:^copy[ ]from[ ](?P<copy_from>.+)\n
            ^copy[ ]to[ ](?P<copy_to>.+)(?:\n|$))?
         (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))?
         (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))?
         (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+)
             \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))?
         (?:^(?P<bin_patch>GIT[ ]binary[ ]patch)(?:\n|$))?
         (?:^---[ ](a/(?P<a_file>.+?)|/dev/null)\t?(?:\n|$))?
         (?:^\+\+\+[ ](b/(?P<b_file>.+?)|/dev/null)\t?(?:\n|$))?
     """, re.VERBOSE | re.MULTILINE)
     _escape_re = re.compile(r'(&)|(<)|(>)|(\t)|(\r)|(?<=.)( \n| $)')
     def __init__(self, diff, vcs='hg', diff_limit=None, inline_diff=True):
         """
         :param diff:   a text in diff format
         :param vcs: type of version control hg or git
         :param diff_limit: define the size of diff that is considered "big"
             based on that parameter cut off will be triggered, set to None
             to show full diff
         """
         if not isinstance(diff, basestring):
             raise Exception('Diff must be a basestring got %s instead' % type(diff))
         self._diff = diff
         self.adds = 0
         self.removes = 0
         self.diff_limit = diff_limit
         self.limited_diff = False
         self.vcs = vcs
         self.parsed = self._parse_gitdiff(inline_diff=inline_diff)
     def _escaper(self, string):
         """
         Do HTML escaping/markup
         """
         def substitute(m):
             groups = m.groups()
             if groups[0]:
                 return '&amp;'
             if groups[1]:
                 return '&lt;'
             if groups[2]:
                 return '&gt;'
             if groups[3]:
                 return '<u>\t</u>'
             if groups[4]:
                 return '<u class="cr"></u>'
             if groups[5]:
                 return ' <i></i>'
             assert False
         return self._escape_re.sub(substitute, safe_unicode(string))
     def _get_header(self, diff_chunk):
         """
         Parses a Git diff for a single file (header and chunks) and returns a tuple with:
 . A dict with meta info:
             a_path, b_path, similarity_index, rename_from, rename_to,
             old_mode, new_mode, new_file_mode, deleted_file_mode,
             a_blob_id, b_blob_id, b_mode, a_file, b_file
 . An iterator yielding lines with simple HTML markup.
         """
         match = None
         if self.vcs == 'git':
             match = self._git_header_re.match(diff_chunk)
         elif self.vcs == 'hg':
             match = self._hg_header_re.match(diff_chunk)
         if match is None:
             raise Exception('diff not recognized as valid %s diff' % self.vcs)
         meta_info = match.groupdict()
         rest = diff_chunk[match.end():]
         if rest and not rest.startswith('@') and not rest.startswith('literal ') and not rest.startswith('delta '):
             raise Exception('cannot parse %s diff header: %r followed by %r' % (self.vcs, diff_chunk[:match.end()], rest[:1000]))
-        diff_lines = (self._escaper(m.group(0)) for m in re.finditer(r'.*\n|.+$', rest)) # don't split on \r as str.splitlines do
         diff_lines = (_escaper(m.group(0)) for m in re.finditer(r'.*\n|.+$', rest)) # don't split on \r as str.splitlines do
         return meta_info, diff_lines
     def _parse_gitdiff(self, inline_diff):
         """Parse self._diff and return a list of dicts with meta info and chunks for each file.
         Might set limited_diff.
         Optionally, do an extra pass and to extra markup of one-liner changes.
         """
         _files = [] # list of dicts with meta info and chunks
         starts = [m.start() for m in self._diff_git_re.finditer(self._diff)]
         starts.append(len(self._diff))
@@ @@ -615,24 +591,51 @@ class DiffProcessor(object): @@
         if old_line != old_end or new_line != new_end:
             raise Exception('diff processing broken when old %s<>%s or new %s<>%s line %r' % (old_line, old_end, new_line, new_end, line))
         return chunks, added, deleted
     def stat(self):
         """
         Returns tuple of added, and removed lines for this instance
         """
         return self.adds, self.removes
 _escape_re = re.compile(r'(&)|(<)|(>)|(\t)|(\r)|(?<=.)( \n| $)')
 def _escaper(string):
     """
     Do HTML escaping/markup
     """
     def substitute(m):
         groups = m.groups()
         if groups[0]:
             return '&amp;'
         if groups[1]:
             return '&lt;'
         if groups[2]:
             return '&gt;'
         if groups[3]:
             return '<u>\t</u>'
         if groups[4]:
             return '<u class="cr"></u>'
         if groups[5]:
             return ' <i></i>'
         assert False
     return _escape_re.sub(substitute, safe_unicode(string))
 # Used for inline highlighter word split, must match the substitutions in _escaper
 _token_re = re.compile(r'()(&amp;|&lt;|&gt;|<u>\t</u>|<u class="cr"></u>| <i></i>|\W+?)')
 def _highlight_inline_diff(old, new):
     """
     Highlight simple add/remove in two lines given as info dicts. They are
     modified in place and given markup with <del>/<ins>.
     """
     assert old['action'] == 'del'
     assert new['action'] == 'add'

0 comments (0 inline, 0 general)